基于YOLOX-WSC的PCB缺陷检测算法研究

doi:10.3778/j.issn.1002-8331.2211-0143

摘要/Abstract

摘要： 针对复杂场景下，PCB缺陷检测难度大、种类多、容易出现误检或漏检的问题，提出一种基于YOLOX-WSC的PCB缺陷检测算法。对输入模型数据进行优化，采用弱化数据增强减少Mosaic引入的不准确图像并提前完成收敛，提升了模型检测效果；在主干网络中添加无参数注意力SimAM，在不增加模型参数的同时使用能量函数评估有效特征，以提升算法的特征提取和定位能力；在特征融合网络中采用CSPHB模块替换CSPLayer结构，获取高阶语义信息，提高分辨能力，同时加强特征融合网络的特征融合交互能力，进而提高模型检测性能。实验结果表明，各模块的改进平均精度均值（mAP）都有不同程度的提升，YOLOX-WSC算法的mAP@0.5达到96.65%，mAP@0.5：0.95达到了79.58%，比YOLOX分别提升了2.88个百分点、11.64个百分点，并且各个类别缺陷平均精度有明显提升，证明了算法的有效性。

关键词: 小目标检测, YOLOX, 无参数注意力, 数据增强, 缺陷检测

Abstract: In view of the difficulty and variety of PCB defect detection in complex scenes, and the problems of false or missed detection are easy to occur, a PCB defect detection algorithm based on YOLOX-WSC is proposed. Firstly, the input model data are optimized, and the weakening data are used to enhance the inaccurate image introduced by Mosaic, and the convergence is completed in advance to improve the model detection effect. Secondly, a parameterless attention SimAM is added to the backbone network to evaluate effective features using energy functions without adding model parameters, so as to improve the feature extraction and localization capability of the algorithm. Finally, the CSPLayer structure is replaced by CSPHB module in the feature fusion network to obtain higher-order semantic information, improve the resolution ability, and strengthen the feature fusion interaction ability of the feature fusion network, so as to improve the model detection performance. The experimental results show that the improved mean precision mAP of each module has been improved to different degrees, the mAP@0.5 of YOLOX-WSC algorithm reaches 96.65%, mAP@0.5：0.95 reaches 79.58%. Compared with YOLOX, the average accuracy of each defect category is significantly improved 2.88 percentage points and 11.64 percentage points, which proves the effectiveness of the algorithm.

Key words: small target detection, YOLOX, non parametric attention, data enhancement, defect detection

庹冰, 黄丽雯, 唐鑫, 谌列勇, 周静. 基于YOLOX-WSC的PCB缺陷检测算法研究[J]. 计算机工程与应用, 2023, 59(10): 236-243.

TUO Bing, HUANG Liwen, TANG Xin, CHEN Lieyong, ZHOU Jing. Research on PCB Defect Detection Algorithm Based on YOLOX-WSC[J]. Computer Engineering and Applications, 2023, 59(10): 236-243.

参考文献

[1] 吴一全，赵朗月，苑玉彬，等.基于机器视觉的PCB缺陷检测算法研究现状及展望[J].仪器仪表学报，2022，43（8）：1-17.
WU Y Q，ZHAO L Y，YUAN Y B，et al.Research status and prospect of PCB defect detection algorithm based on machine vision[J].Chinese Journal of Scientific Instrument，2022，43（8）：1-17.
[2] 陈世哲.微电子产品视觉检测中关键技术研究[D].哈尔滨：哈尔滨工业大学，2006.
CHENG S Z.Research on key technologies in visual in spection of microelectronic products[D].Harbin：Harbin Institute of Technology，2006.
[3] REDMON J，DIVVALA S，UIRSHICK R，et al.You only look once：unified，real-time object detection[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recogition，Las Vegas，2016：779-788.
[4] REDMON J，FARHADI A.YOLOv3：an incremental improvement[J].ArXiv：1804.02767，2018.
[5] BOCHKOVSKIY A，WANG C Y，LIAO H Y M.YOLOv4：optimal speed and accuracy of object detection[J].arXiv：2004.10934，2020.
[6] 牛洪超，白松，胡晓兵.基于改进YOLOv5的视觉定位算法[J].计算机工程与设计，2022，43（6）：1620-1627.
NIU H C，BAI S，HU X B.Visual localization algorithm based on improved YOLOv5[J].Computer Engineering and Design，2022，43（6）：1620-1627.
[7] 胡均平，王鸿树，戴小标，等.改进YOLOv5的小目标交通标志实时检测算法[J].计算机工程与应用，2023，59（2）：185-193.
HU J P，WANG H S，DAI X B，et al.Real-time detection algorithm for small-target traffic signs based on improved YOLOv5[J].Computer Engineering and Applicationts，2023，59（2）：185-193.
[8] 李冬伟，丁力，梁栋.基于改进YOLOv3的纽扣电池表面缺陷检[J].机械制造与自动化，2022，51（5）：177-181.
LI D W，DING L，LIANG D.Surface defect detection of button battery based on improved YOLOv3[J].Machine Building & Automation，2022，51（5）：177-181.
[9] GE Z，LIU S，WANG F，et al.YOLOX：exceeding YOLO series in 2021[J].arXiv：2107.08430，2021.
[10] HE K，ZHANG X，REN S，et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2015，37（9）：1904-1916.
[11] 李亚东，马行，穆春阳，等.改进YOLOX网络的轴承缺陷小目标检测方法[J].计算机工程与应用，2023，59（1）：100-107.
LI Y D，MA X，MU C Y，et al.Small target detection method for bearing defects based on improved YOLOX network[J].Computer Engineering and Applications，2023，59（1）：100-107.
[12] 丁田，陈向阳，周强，等.基于改进YOLOX的安全帽佩戴实时检测[J].电子测量技术，2022，45（17）：72-78.
DING T，CHEN X Y，ZHOU Q，et al.Real-time detection of helmet wearing based on improved YOLOX[J].Electronic Measurement Technology，2022，45（17）：72-78.
[13] 胡海涛，杜昊晨，王素琴，等.改进YOLOX的药品泡罩铝箔表面缺陷检测方法[J].图学学报，2022，43（5）：803-814.
HU H T，DU H C，WANG S Q，et al.Improved YOLOX method for detecting surface defects of drug blister aluminum foil[J].Journal of Graphics，2022，43（5）：803-814.
[14] 郎磊，刘宽，王东.基于YOLOX-Tiny的轻量级遥感图像目标检测模型[J].激光与光电子学进展，2023，60（2）：362-372.
LANG L，LIU K，WANG D.Lightweight remote sensing image target detection model based on YOLOX-Tiny[J].Advances in Laser and Optoelectronics2023，60（2）：362-372.
[15] 林成创，赵淦森，尹爱华，等.AS-PANet：改进路径增强网络的重叠染色体实例分割[J].中国图象图形学报，2020，25（10）：2271-2280.
LIN C C，ZHAO G S，YIN A H，et al.AS-PANet：an improved path enhancement network for overlapping chromosome instance segmentation[J].Journal of Image and Graphics，2020，25（10）：2271-2280.
[16] ZHANG T W，ZHANG X L，KE X.Quad-CPN：a novel quad feature pyramid network for SAR ship detection[J].Remote Sensing，2021，13（14）：2771.
[17] YANG L X，ZHANG R Y.SimAM：a simple，parameter-free attention module for convolutional neural networks[C]//Proceedings of the 38th International Conference on Machine Learning，New York，2021：11863.
[18] WANG C Y，LIAO H Y M，WU Y H，et al.CSPNet：a new backbone that can enhance learning capability of CNN[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops，Seattle，2020：1571-1580.
[19] RAO Y M，ZHAO W L，TANG Y S，et al.HoNet：efficient high-order spatial interactions with recursive gated convolutions[J].arXiv：2207.14284，2022.
[20] HU J，SHEN L，ALBANIE S，et al.Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，Salt Lake City，2018：7132-7141.